reputation
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted feedback and metadata from the Stacks blockchain, which could serve as a vector for indirect prompt injection.
- Ingestion points: Data is retrieved from the blockchain using the
read-feedbackandread-all-feedbacktools inreputation/reputation.ts. - Boundary markers: No specific boundary markers or instructions are provided to help the agent differentiate between data and potentially malicious instructions within the feedback content.
- Capability inventory: The skill possesses several active write capabilities, including
give-feedback,revoke-feedback,append-response, andapprove-client, which could be exploited if an injection is successful. - Sanitization: The implementation validates data types and hex formats but does not perform content-based sanitization of text fields or URIs.
Audit Metadata